Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

TLDR

The authors propose a simple solution that uses a single NMT model to translate between multiple languages. The approach adds an artificial token to the input to specify the target language, uses a shared wordpiece vocabulary, and requires no changes to the standard NMT architecture. On WMT benchmarks the multilingual model matches English→French performance and outperforms state‑of‑the‑art for English→German, French→English, and German→English; on production data it improves many language pairs and demonstrates zero‑shot translation and a universal interlingua representation.

Abstract

We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no changes to the model architecture from a standard NMT system but instead introduces an artificial token at the beginning of the input sentence to specify the required target language. Using a shared wordpiece vocabulary, our approach enables Multilingual NMT systems using a single model. On the WMT’14 benchmarks, a single multilingual model achieves comparable performance for English→French and surpasses state-of-theart results for English→German. Similarly, a single multilingual model surpasses state-of-the-art results for French→English and German→English on WMT’14 and WMT’15 benchmarks, respectively. On production corpora, multilingual models of up to twelve language pairs allow for better translation of many individual pairs. Our models can also learn to perform implicit bridging between language pairs never seen explicitly during training, showing that transfer learning and zero-shot translation is possible for neural translation. Finally, we show analyses that hints at a universal interlingua representation in our models and also show some interesting examples when mixing languages.